Field
Innovation and Entrepreneurship
Date
April 2026
Abstract
Shoulder injuries represent the most prevalent form of overuse injury among elite aquatic athletes, among competitive swimmers, reported rates of injured shoulders vary from 40% to 91% across different studies [1]. However, they frequently remain undetected until they progress to more advanced and clinically significant stages. This gap in early identification limits opportunities for timely intervention and injury prevention. The proposed project seeks to address this critical issue by leveraging wearable inertial measurement unit (IMU) sensors in combination with advanced machine learning techniques to enable objective, continuous monitoring of shoulder biomechanics. Specifically, this study will enroll a cohort of 40 collegiate swimmers and water polo players to collect high-resolution movement data during training and competition. By analyzing these data, the project aims to develop robust models capable of detecting subtle biomechanical deviations and shoulder injury risk.
Recommended Citation
Gronbach, Ben and Capili, Kyle, "Analyzing Kinematic Data with Machine Learning to Detect Injuries in Swimmers" (2026). Pacific Innovation and Entrepreneurship Summit (PIES). 56.
https://scholarlycommons.pacific.edu/pies/56
